GP

Huihui Gpt Oss 20b BF16 Abliterated

gpt-ossGGUF by gabriellarsonUpdated 2025-08-07
Download on Hugging Face
Parameters20.9B
Context128K
Layers24
Architecturegpt-oss
Smallest quant12.1 GB
Quick answer

Huihui Gpt Oss 20b BF16 Abliterated needs about 16.7 GB of memory at BF16 (a 15.8 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 3 quants, from 12.1 GB (BF16) to 41.9 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 1.6 GB.

Huihui Gpt Oss 20b BF16 Abliterated is a 20.9B-parameter gpt-oss model in GGUF format, quantized by gabriellarson. Its trained context length is 128K tokens. The repository has 3 quant files, from 12.1 GB (BF16) to 41.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
BF1612.1 GB 13.0 GB
Too big Get file →
BF1615.8 GB 16.7 GB
Too big Get file →
F1641.9 GB 42.8 GB
Too big Get file →

What GPU do you need for Huihui Gpt Oss 20b BF16 Abliterated?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: the best quant that fits is BF16 (12.1 GB file, about 13.0 GB in use).
  • 24 GB VRAM: the best quant that fits is BF16 (15.8 GB file, about 16.7 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (15.8 GB file, about 16.7 GB in use).
  • 48 GB VRAM: the best quant that fits is F16 (41.9 GB file, about 42.8 GB in use).

Which Huihui Gpt Oss 20b BF16 Abliterated quant should you choose?

BF16 (15.8 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

If memory is tight, the smallest file is BF16 at 12.1 GB, with the quality trade-offs that come with fewer bits. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturegpt-oss
Parameters20.9B (approximate, mixture of experts)
Layers24
Trained context131,072 tokens
KV cache (fp16)48 KB per token

Source

Quantized bygabriellarson
Familygpt-oss
Licenseapache-2.0
Downloads (HF)165
Last updated2025-08-07

Frequently asked questions about Huihui Gpt Oss 20b BF16 Abliterated

How much VRAM does Huihui Gpt Oss 20b BF16 Abliterated need?

About 16.7 GB at BF16 with an 8K context window. That is the 15.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Huihui Gpt Oss 20b BF16 Abliterated on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 13.0 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Huihui Gpt Oss 20b BF16 Abliterated GGUF?

It depends on the quant: BF16 is 12.1 GB, BF16 is 15.8 GB, F16 is 41.9 GB.

What context length does Huihui Gpt Oss 20b BF16 Abliterated support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.4 GB at 8K and 1.6 GB at 32K.

Where can I download Huihui Gpt Oss 20b BF16 Abliterated GGUF?

The files are on Hugging Face in the gabriellarson/Huihui-gpt-oss-20b-BF16-abliterated-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Huihui Gpt Oss 20b BF16 Abliterated use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Other GGUFs of Huihui-gpt-oss-20b-BF16-abliterated

Similar models

Browse all →

More from gabriellarson

All by gabriellarson →

More gpt-oss models

All gpt-oss →

Other medium models

All medium models →